agentleFS
Sign inStart free
jazzychadjazzychad/ios-code-audit/CLAUDE.md

ios-code-audit

CLAUDE.md36 starsChanged 6 months agoMITView on GitHub

A single Claude Code skill (ios-code-audit) that produces a CODE_AUDIT.md report for an iOS/macOS Swift project. There is no application code, build system, or test suite here — the "deliverables" are the prompts that drive an audit run against some other Swift codebase. When the user invokes this skill, Claude is operating in the user's iOS project directory, not this one. Edits in this repo only change future audit behavior. The three files form a single pipeline: SKILL.md drives the…

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 2

    1. VelimirMueller/ai-development-skills★ 7100% same
    2. VelimirMueller/claude-skills★ 7100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this CLAUDE.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user invokes this skill, Claude is operating in the user's iOS project directory, *not* this one.

    line 9

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

A single Claude Code skill (ios-code-audit) that produces a CODE_AUDIT.md report for an iOS/macOS Swift project. There is no application code, build system, or test suite here — the "deliverables" are the prompts that drive an audit run against some other Swift codebase.

When the user invokes this skill, Claude is operating in the user's iOS project directory, not this one. Edits in this repo only change future audit behavior.

File layout

  • SKILL.md — the skill definition and the 6-step workflow Claude follows when invoked. This is the source of truth; everything else is referenced from it.
  • references/agent-prompts.md — copy-paste briefs for the three parallel Explore agents (concurrency/API modernity, dead code/duplication, bugs/security/performance). Contains a placeholder table at the bottom showing how each {PLACEHOLDER} is discovered.
  • references/report-template.md — the CODE_AUDIT.md skeleton with section numbering. Section numbers (3.1, 3.2, …) are stable across edits by design so user notes referencing "§5.4" don't shift.

The three files form a single pipeline: SKILL.md drives the workflow, the agent prompts produce raw findings, and the report template structures them.

Editing rules specific to this skill

  • Severity discipline is the load-bearing invariant. SKILL.md enforces a four-level guide (Critical/High/Medium/Low) and requires spot-verification of every Critical claim before it lands in the report. Don't loosen this — it's a direct response to past runs where agents overstated severity.
  • The three agents must run in parallel. agent-prompts.md repeats this: "send all three in a single message with multiple Agent tool calls." If you edit the workflow, preserve the parallel-launch requirement.
  • Per-finding template is identical across all three agent briefs. If you change the format (Location/What/Why/Action/Severity), update it in all three briefs and the report template in lockstep — synthesis depends on it being mechanical.
  • Dead/ (or any explicitly-archived directory) is excluded by default. The skill expects to read the audited project's own CLAUDE.md to discover excluded paths.

What the skill explicitly does not cover

Listed in SKILL.md under "What this skill does NOT cover" — Metal kernel correctness, Xcode project structure, third-party dependencies, deep test coverage, localization wording, Instruments profiling. Keep that list in sync if scope changes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free